Sökning: "TREC"

Visar resultat 1 - 5 av 10 uppsatser innehållade ordet TREC.

  1. 1. Investigating Search Algorithms for Shorter Documents : A study on how to search for titles

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Lara Rostami; [2022]
    Nyckelord :information retrieval; search engine; search algorithm; BM25; short documents; titles; title search; informationssökning; sökmotor; sökalgoritm; BM25; korta dokument; titlar; titelsökning;

    Sammanfattning : The objective of this thesis was to explore whether there are alternatives to the established search ranking algorithm Best Matching 25 (BM25) when searching for shorter documents, in particular for the search of titles. Five search engines were compared to BM25, three of them being variants of the BM25 algorithm and the other two being based on a binary independence model that does not take term frequency or length normalisation into account. LÄS MER

  3. 2. What the BERT? : Fine-tuning KB-BERT for Question Classification

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Jonatan Cervall; [2021]
    Nyckelord :BERT; KB-BERT; Question Classification; TREC; Li and Roth Taxonomy; BERT; KB-BERT; Frågeklassificering; TREC; Li och Roth Taxonomi;

    Sammanfattning : This work explores the capabilities of KB-BERT on the downstream task of Question Classification. The TREC data set for Question Classification with the Li and Roth taxonomy was translated to Swedish, by manually correcting the output of Google’s Neural Machine Translation. 500 new data points were added. LÄS MER

  4. 3. Rocchio, Ide, Okapi och BIM : En komparativ studie av fyra metoder för relevance feedback

    Magister-uppsats, Högskolan i Borås/Institutionen Biblioteks- och informationsvetenskap / Bibliotekshögskolan

    Författare :Martin Eriksen; [2008]
    Nyckelord :relevance feedback; information retrieval; rocchio; ide dec-hi; okapi bm25; vektormodellen; sökfrågeexpansion; klassiska probabilistiska modellen;

    Sammanfattning : This thesis compares four relevance feedback methods. The Rocchio and Ide dec-hi algorithms for the vector space model and the binary independence model and Okapi BM25 within the probabilistic framework. LÄS MER

  5. 4. Nominalfrasers inverkan på återvinningseffektiviteten i ett probabilistiskt IR-system

    Magister-uppsats, Högskolan i Borås/Institutionen Biblioteks- och informationsvetenskap / Bibliotekshögskolan

    Författare :Ylva Persson; [2007]
    Nyckelord :nominalfraser; ordboksfraser; återvinningseffektivitet; information retrieval; QPA; frasoperatorer; sökfrågor;

    Sammanfattning : The purpose of this study is to examine the difference between three query strategies with respect to retrieval effectiveness. The thesis aims at examining how two types of noun phrases containing a modifier to the head word, which is a noun affect the retrieval performance with regard to recall and precision. LÄS MER

  7. 5. Effekten av avståndsoperatorer samt expansion med synonymer med avseende på återvinningseffektiviteten

    Magister-uppsats, Högskolan i Borås/Institutionen Biblioteks- och informationsvetenskap / Bibliotekshögskolan

    Författare :Emma Elofsson; [2006]
    Nyckelord :library and information science; biblioteks- och informationsvetenskap;

    Sammanfattning : This thesis examines the effects of proximity operators and query expansion with synonyms on retrieval performance. The queries were expanded with synonyms and structured with proximity operators where the permitted distance between terms varied from 1 to 3. The expansion terms were selected from the online lexical reference system WordNet. LÄS MER